让检索模型理解与、或、非逻辑，提升复杂查询准确率
Boolean-aware Attention for Dense Retrieval
- 为布尔运算符设计专用注意力专家，动态调节关键词权重
- 在多个数据集上显著提升布尔查询的检索效果
- 适合需要精准逻辑匹配的搜索引擎和问答系统
我们提出一种新型注意力机制——布尔感知注意力（BoolAttn），能根据布尔运算符（如and、or、not）动态调整词语关注程度。模型引入专门的布尔专家，针对不同运算符上下文增强或抑制注意力。通过预设门控机制，根据检测到的布尔类型激活相应专家。在布尔检索数据集上的实验表明，将BoolAttn集成到BERT中，显著提升了模型处理布尔查询的能力。
原文摘要 · Abstract (English)
We present Boolean-aware attention, a novel attention mechanism that dynamically adjusts token focus based on Boolean operators (e.g., and, or, not). Our model employs specialized Boolean experts, each tailored to amplify or suppress attention for operator-specific contexts. A predefined gating mechanism activates the corresponding experts based on the detected Boolean type. Experiments on Boolean retrieval datasets demonstrate that integrating BoolAttn with BERT greatly enhances the model's capability to process Boolean queries.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。